Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 2 — central limit theorem for the TPG estimator and consistency of the nonstationary HAC variance estimator

Proved
TPG.theorem_2_clt_and_hac

by Wenqian Xing · Oct 12, 2026 · Mathlib 0df444a (Lean v4.33.1)

causal-inferencemarkov-chainnonstationaritypolicy-gradienttreatment-effect

Setting. SSS is a finite state space and the action Zt∈{0,1}Z_t\in\{0,1\}Zt​∈{0,1} is control or treatment. Time is t=0,1,…,T−1t=0,1,\dots,T-1t=0,1,…,T−1, which is the source's time t+1t+1t+1. Under action zzz at time ttt the state moves according to a transition matrix PztP_z^tPzt​, i.e. P(Xt+1=x′∣Xt=x,Zt=z)=Pzt(x,x′)\mathbb P(X_{t+1}=x'\mid X_t=x,Z_t=z)=P_z^t(x,x')P(Xt+1​=x′∣Xt​=x,Zt​=z)=Pzt​(x,x′); the matrices may depend on ttt arbitrarily. The initial state X0X_0X0​ has distribution ρ\rhoρ, and the reward YtY_tYt​ has distribution R(⋅∣Xt,Zt)R(\cdot\mid X_t,Z_t)R(⋅∣Xt​,Zt​) on R\mathbb RR, with R([−M,M]∣x,z)=1R([-M,M]\mid x,z)=1R([−M,M]∣x,z)=1 for all x,zx,zx,z and conditional independence from everything else given (Xt,Zt)(X_t,Z_t)(Xt​,Zt​). Under the policy πθ\pi_\thetaπθ​ every action is treatment with probability θ\thetaθ, independently of everything else; Eθ\mathbb E_\thetaEθ​, Pθ\mathbb P_\thetaPθ​ and Var⁡θ\operatorname{Var}_\thetaVarθ​ refer to the law of the trajectory (Xt,Zt,Yt)t<T(X_t,Z_t,Y_t)_{t<T}(Xt​,Zt​,Yt​)t<T​ under πθ\pi_\thetaπθ​.

Asymptotic setting. The truncation size k≥0k\ge0k≥0 is fixed and the horizon T→∞T\to\inftyT→∞; for each TTT the trajectory (Xt,Zt,Yt)t<T(X_t,Z_t,Y_t)_{t<T}(Xt​,Zt​,Yt​)t<T​ is generated under the experimental policy π1/2\pi_{1/2}π1/2​. Assumption 1 holds for all times with one constant γ∈(0,1)\gamma\in(0,1)γ∈(0,1). Write wtIPW=2(2Zt−1)w_t^{\mathrm{IPW}}=2(2Z_t-1)wtIPW​=2(2Zt​−1) and

Bt=∑i=max⁡(0,t−k)twiIPW Yt,μt=E[Bt],Bˉ=1T∑t<TBt=τ^k.B_t=\sum_{i=\max(0,t-k)}^{t}w_i^{\mathrm{IPW}}\,Y_t,\qquad \mu_t=\mathbb E[B_t],\qquad \bar B=\frac1T\sum_{t<T}B_t=\widehat\tau_k .Bt​=i=max(0,t−k)∑t​wiIPW​Yt​,μt​=E[Bt​],Bˉ=T1​t<T∑​Bt​=τk​.

Assumption 2 (asymptotic variance): 1TVar⁡(∑t<TBt)→σk2\frac1T\operatorname{Var}\bigl(\sum_{t<T}B_t\bigr)\to\sigma_k^2T1​Var(∑t<T​Bt​)→σk2​ as T→∞T\to\inftyT→∞, with 0<σk2<∞0<\sigma_k^2<\infty0<σk2​<∞.

Assumption 3 (Cesàro-L2L^2L2 mean stability): with μˉT=1T∑t<Tμt\bar\mu_T=\frac1T\sum_{t<T}\mu_tμˉ​T​=T1​∑t<T​μt​,  ΔT2=1T∑t<T(μt−μˉT)2=o(T−2/3)\ \Delta_T^2=\frac1T\sum_{t<T}(\mu_t-\bar\mu_T)^2=o(T^{-2/3}) ΔT2​=T1​∑t<T​(μt​−μˉ​T​)2=o(T−2/3).

The bandwidth LTL_TLT​ is a deterministic integer sequence with 0≤LT<T0\le L_T<T0≤LT​<T for every T≥1T\ge1T≥1, LT→∞L_T\to\inftyLT​→∞ and LT=O(T1/3)L_T=O(T^{1/3})LT​=O(T1/3), and wℓNW=1−ℓ/(LT+1)w_\ell^{\mathrm{NW}}=1-\ell/(L_T+1)wℓNW​=1−ℓ/(LT​+1).

With V^t=Bt−Bˉ\widehat V_t=B_t-\bar BVt​=Bt​−Bˉ, the nonstationary HAC variance estimator is

Γ^ℓ=1T∑t+ℓ<TV^t V^t+ℓ,Ω^T=Γ^0+2∑ℓ=1LTwℓNW Γ^ℓ.\widehat\Gamma_\ell=\frac1T\sum_{t+\ell<T}\widehat V_t\,\widehat V_{t+\ell},\qquad \widehat\Omega_T=\widehat\Gamma_0+2\sum_{\ell=1}^{L_T}w_\ell^{\mathrm{NW}}\,\widehat\Gamma_\ell .Γℓ​=T1​t+ℓ<T∑​Vt​Vt+ℓ​,ΩT​=Γ0​+2ℓ=1∑LT​​wℓNW​Γℓ​.

Theorem. Under Assumptions 1, 2 and 3, as T→∞T\to\inftyT→∞,

T (τ^k−E[τ^k]) ⇒ N(0,σk2),Ω^T →p σk2,\sqrt T\,\bigl(\widehat\tau_k-\mathbb E[\widehat\tau_k]\bigr)\ \Rightarrow\ \mathcal N\bigl(0,\sigma_k^2\bigr),\qquad \widehat\Omega_T\ \xrightarrow{p}\ \sigma_k^2 ,T​(τk​−E[τk​]) ⇒ N(0,σk2​),ΩT​ p​ σk2​,

where τ^k=1T∑u=0T−1(1{Zu=1}1/2−1{Zu=0}1/2)∑t=umin⁡(u+k, T−1)Yt\widehat\tau_k=\frac1T\sum_{u=0}^{T-1}\bigl(\frac{\mathbf 1\{Z_u=1\}}{1/2}-\frac{\mathbf 1\{Z_u=0\}}{1/2}\bigr)\sum_{t=u}^{\min(u+k,\,T-1)}Y_tτk​=T1​∑u=0T−1​(1/21{Zu​=1}​−1/21{Zu​=0}​)∑t=umin(u+k,T−1)​Yt​ is the TPG estimator.

The theorem gives an estimated standard error Ω^T/T\sqrt{\widehat\Omega_T/T}ΩT​/T​ for the TPG estimator from a single nonstationary trajectory, and hence confidence intervals for E[τ^k]\mathbb E[\widehat\tau_k]E[τk​].

Formalization Note For each TTT the statistics are computed under the horizon-TTT law. Convergence in distribution is stated as convergence of E[f(⋅)]\mathbb E[f(\cdot)]E[f(⋅)] for every bounded continuous fff, and convergence in probability as P(∣Ω^T−σk2∣≥ε)→0\mathbb P(|\widehat\Omega_T-\sigma_k^2|\ge\varepsilon)\to0P(∣ΩT​−σk2​∣≥ε)→0 for every ε>0\varepsilon>0ε>0. The limit σk2\sigma_k^2σk2​ is a parameter vvv constrained by Assumption 2.

Preamble
import Mathlib
import Definitions.Def_TPG_Model
import Definitions.Def_TPG_Estimators
import Definitions.Def_TPG_Inference

open MeasureTheory ProbabilityTheory
open scoped BigOperators ENNReal
Formal statement
namespace TPG
theorem theorem_2_clt_and_hac {S : Type} [Fintype S] [MeasurableSpace S] [MeasurableSingletonClass S]
    (E : Env S) (k : ℕ) (γ M v : ℝ) (L : ℕ → ℕ)
    (hγ0 : 0 < γ) (hγ1 : γ < 1) (hmix : ∀ T : ℕ, E.Mixing T γ) (hM : E.RewardBound M)
    (hvar : E.AsymptoticVariance k v) (hstab : E.MeanStability k) (hL : IsBandwidth L) :
    E.TendstoNormal
        (fun (T : ℕ) (ω : Traj S T) =>
          Real.sqrt (T : ℝ) *
            (tpgEst (1 / 2) T k ω - ∫ ω', tpgEst (1 / 2) T k ω' ∂(E.expLaw T (1 / 2))))
        v
      ∧ E.TendstoInProb (fun (T : ℕ) (ω : Traj S T) => hacEst T k (L T) ω) v := by sorry
end TPG
Source
Johari, Peng, Xing, Estimation of Treatment Effects Under Nonstationarity via the Truncated Policy Gradient Estimator, revised manuscript of October 2026 (revision of arXiv:2506.05308v3, https://arxiv.org/abs/2506.05308); numbering follows the revised manuscript. §6 (Nonstationary CLT and variance estimation), p. 17, Assumptions 2–3 and Theorem 2; proof in Appendix F.2, pp. 41–42, via Lemmas 3–5.
Read-back

What the Lean code literally says, in plain math · claude-opus-5-5

Data quantified over. The statement is asserted for every choice of the following.

  • A set SSS with finitely many elements, carrying a σ\sigmaσ-algebra in which every one-point set is measurable (as SSS is finite, every subset of SSS is then measurable). Non-emptiness of SSS is not listed as an assumption, but the datum ρ\rhoρ below cannot exist on an empty set.
  • An environment EEE on SSS, i.e. a package consisting of:
    • for every time t∈N={0,1,2,… }t \in \mathbb{N} = \lbrace 0,1,2,\dots \rbracet∈N={0,1,2,…} and every z∈{true,false}z \in \lbrace \text{true}, \text{false} \rbracez∈{true,false}, a real S×SS \times SS×S matrix PtzP_t^{z}Ptz​ all of whose entries are ≥0\ge 0≥0 and each of whose rows sums to 111;
    • a function ρ:S→R\rho : S \to \mathbb{R}ρ:S→R with ρ(x)≥0\rho(x) \ge 0ρ(x)≥0 for every xxx and ∑x∈Sρ(x)=1\sum_{x \in S} \rho(x) = 1∑x∈S​ρ(x)=1;
    • for every x∈Sx \in Sx∈S and z∈{true,false}z \in \lbrace \text{true}, \text{false} \rbracez∈{true,false}, a Borel probability measure Rx,zR_{x,z}Rx,z​ on R\mathbb{R}R (the package itself imposes no moment or support condition on it).
  • A natural number kkk (any value, 000 included; one fixed number, not varying with TTT).
  • Real numbers γ\gammaγ, MMM, vvv.
  • A function L:N→NL : \mathbb{N} \to \mathbb{N}L:N→N.

Sample space and probability measure, one for each TTT. For each T∈NT \in \mathbb{N}T∈N let

ΩT=(S×{true,false}×R)T,\Omega_T = \bigl(S \times \lbrace \text{true}, \text{false} \rbrace \times \mathbb{R}\bigr)^{T},ΩT​=(S×{true,false}×R)T,

the set of sequences ω=(Xt,Zt,Yt)t=0T−1\omega = (X_t, Z_t, Y_t)_{t = 0}^{T-1}ω=(Xt​,Zt​,Yt​)t=0T−1​, with the product σ\sigmaσ-algebra (the given σ\sigmaσ-algebra on SSS, all subsets of {true,false}\lbrace \text{true}, \text{false} \rbrace{true,false}, Borel sets of R\mathbb{R}R). Write Xt(ω)∈SX_t(\omega) \in SXt​(ω)∈S, Zt(ω)∈{true,false}Z_t(\omega) \in \lbrace \text{true}, \text{false} \rbraceZt​(ω)∈{true,false}, Yt(ω)∈RY_t(\omega) \in \mathbb{R}Yt​(ω)∈R for the coordinates at time ttt.

For x=(x0,…,xT−1)∈STx = (x_0, \dots, x_{T-1}) \in S^Tx=(x0​,…,xT−1​)∈ST and z=(z0,…,zT−1)∈{true,false}Tz = (z_0, \dots, z_{T-1}) \in \lbrace \text{true}, \text{false} \rbrace^Tz=(z0​,…,zT−1​)∈{true,false}T define the weight

wT(x,z)=ρ(x0)⋅∏s=0T−2Pszs(xs,xs+1)⋅∏t=0T−112.w_T(x, z) = \rho(x_0) \cdot \prod_{s=0}^{T-2} P_s^{z_s}(x_s, x_{s+1}) \cdot \prod_{t=0}^{T-1} \tfrac12 .wT​(x,z)=ρ(x0​)⋅s=0∏T−2​Pszs​​(xs​,xs+1​)⋅t=0∏T−1​21​.

(The transition from time sss to time s+1s+1s+1 uses the matrix indexed by the departure time sss and by the value zsz_szs​. The last product comes from a general recipe "factor qtq_tqt​ if ztz_tzt​ is true, 1−qt1 - q_t1−qt​ if false", used here with qt=12q_t = \tfrac12qt​=21​ for all ttt. Empty products are 111: for T=0T = 0T=0 the weight is 111, and the factor ρ(x0)\rho(x_0)ρ(x0​) is present only when T≥1T \ge 1T≥1.) The measure on ΩT\Omega_TΩT​ is the finite mixture of product measures

PT=∑(x,z)∈ST×{true,false}Tmax⁡(wT(x,z),0)⋅⨂t=0T−1(δxt⊗δzt⊗Rxt,zt).\mathbb{P}_T = \sum_{(x,z) \in S^T \times \lbrace \text{true}, \text{false} \rbrace^T} \max\bigl(w_T(x,z), 0\bigr) \cdot \bigotimes_{t=0}^{T-1} \bigl( \delta_{x_t} \otimes \delta_{z_t} \otimes R_{x_t, z_t} \bigr).PT​=(x,z)∈ST×{true,false}T∑​max(wT​(x,z),0)⋅t=0⨂T−1​(δxt​​⊗δzt​​⊗Rxt​,zt​​).

The clipping max⁡(⋅,0)\max(\cdot, 0)max(⋅,0) is in the definition; here every weight is already ≥0\ge 0≥0 and the weights sum to 111, so PT\mathbb{P}_TPT​ is a probability measure. In words: X0X_0X0​ has law ρ\rhoρ; each ZtZ_tZt​ is a fair coin flip independent of everything generated before it and of XtX_tXt​; Xt+1X_{t+1}Xt+1​ is drawn from row XtX_tXt​ of PtZtP_t^{Z_t}PtZt​​; and, given all the XXX's and ZZZ's, the YtY_tYt​ are independent with Yt∼RXt,ZtY_t \sim R_{X_t, Z_t}Yt​∼RXt​,Zt​​. For T=0T = 0T=0, Ω0\Omega_0Ω0​ is a single point and P0\mathbb{P}_0P0​ is the unit mass on it. Write ET[⋅]\mathbb{E}_T[\cdot]ET​[⋅] for integration against PT\mathbb{P}_TPT​.

Statistics on ΩT\Omega_TΩT​. Throughout, 1/T1/T1/T is read as 000 when T=0T = 0T=0 (so every statistic below is 000 at T=0T = 0T=0), all integrals are Bochner integrals (value 000 if the integrand is not integrable), and Var⁡μ(F)\operatorname{Var}_\mu(F)Varμ​(F) means ∫∣F−∫Fdμ∣2dμ\int \lvert F - \int F d\mu \rvert^2 d\mu∫∣F−∫Fdμ∣2dμ computed in [0,∞][0, \infty][0,∞] and then converted to a real number with ∞\infty∞ sent to 000.

Two sign weights occur. The first is s(z)=1/θs(z) = 1/\thetas(z)=1/θ if zzz is true and −1/(1−θ)-1/(1-\theta)−1/(1−θ) if zzz is false, evaluated at θ=12\theta = \tfrac12θ=21​: so s(true)=2s(\text{true}) = 2s(true)=2, s(false)=−2s(\text{false}) = -2s(false)=−2. The second is a(z)=2⋅(2⋅1[z=true]−1)a(z) = 2 \cdot (2 \cdot \mathbf{1}[z = \text{true}] - 1)a(z)=2⋅(2⋅1[z=true]−1): so a(true)=2a(\text{true}) = 2a(true)=2, a(false)=−2a(\text{false}) = -2a(false)=−2.

The centred and scaled statistic in the first conclusion is built from

GT(ω)=1T∑u=0T−1s(Zu)∑t=umin⁡(u+k,T−1)Yt,WT(ω)=T⋅(GT(ω)−ET[GT]),G_T(\omega) = \frac{1}{T} \sum_{u=0}^{T-1} s(Z_u) \sum_{t = u}^{\min(u+k, T-1)} Y_t , \qquad W_T(\omega) = \sqrt{T} \cdot \bigl( G_T(\omega) - \mathbb{E}_T[G_T] \bigr),GT​(ω)=T1​u=0∑T−1​s(Zu​)t=u∑min(u+k,T−1)​Yt​,WT​(ω)=T​⋅(GT​(ω)−ET​[GT​]),

where the inner sum runs over the times t∈{0,…,T−1}t \in \lbrace 0, \dots, T-1 \rbracet∈{0,…,T−1} with u≤t≤u+ku \le t \le u + ku≤t≤u+k (so it is cut off at the horizon T−1T-1T−1), and the centring constant is the PT\mathbb{P}_TPT​-expectation of GTG_TGT​ itself.

The second conclusion and two of the hypotheses are built from, for t∈{0,…,T−1}t \in \lbrace 0, \dots, T-1 \rbracet∈{0,…,T−1},

BT,t(ω)=∑i=max⁡(t−k,0)ta(Zi)⋅Yt,B_{T,t}(\omega) = \sum_{i = \max(t-k, 0)}^{t} a(Z_i) \cdot Y_t ,BT,t​(ω)=i=max(t−k,0)∑t​a(Zi​)⋅Yt​,

(the sum is over the indices i∈{0,…,T−1}i \in \lbrace 0, \dots, T-1 \rbracei∈{0,…,T−1} with i≤t≤i+ki \le t \le i + ki≤t≤i+k), together with

BˉT(ω)=1T∑t=0T−1BT,t(ω),Γ^T,ℓ(ω)=1T∑t=0T−1−ℓ(BT,t(ω)−BˉT(ω))(BT,t+ℓ(ω)−BˉT(ω))(ℓ∈N),\bar B_T(\omega) = \frac1T \sum_{t=0}^{T-1} B_{T,t}(\omega), \qquad \widehat\Gamma_{T,\ell}(\omega) = \frac1T \sum_{t=0}^{T-1-\ell} \bigl( B_{T,t}(\omega) - \bar B_T(\omega) \bigr)\bigl( B_{T,t+\ell}(\omega) - \bar B_T(\omega) \bigr) \quad (\ell \in \mathbb{N}),BˉT​(ω)=T1​t=0∑T−1​BT,t​(ω),ΓT,ℓ​(ω)=T1​t=0∑T−1−ℓ​(BT,t​(ω)−BˉT​(ω))(BT,t+ℓ​(ω)−BˉT​(ω))(ℓ∈N),

(the sum is over pairs of indices t,t′∈{0,…,T−1}t, t' \in \lbrace 0, \dots, T-1 \rbracet,t′∈{0,…,T−1} with t′=t+ℓt' = t + \ellt′=t+ℓ; it is empty, hence 000, when ℓ≥T\ell \ge Tℓ≥T; the normalisation is 1/T1/T1/T at every lag), and

H^T(ω)=Γ^T,0(ω)+2∑ℓ=1L(T)(1−ℓL(T)+1)Γ^T,ℓ(ω).\widehat H_T(\omega) = \widehat\Gamma_{T,0}(\omega) + 2 \sum_{\ell = 1}^{L(T)} \Bigl( 1 - \frac{\ell}{L(T) + 1} \Bigr) \widehat\Gamma_{T,\ell}(\omega).HT​(ω)=ΓT,0​(ω)+2ℓ=1∑L(T)​(1−L(T)+1ℓ​)ΓT,ℓ​(ω).

The deterministic quantities used in the hypotheses are

mT,t=ET[BT,t],VT=1TVar⁡PT(∑t=0T−1BT,t),DT=1T∑t=0T−1(mT,t−1T∑s=0T−1mT,s)2.m_{T,t} = \mathbb{E}_T[B_{T,t}], \qquad V_T = \frac1T \operatorname{Var}_{\mathbb{P}_T}\Bigl( \sum_{t=0}^{T-1} B_{T,t} \Bigr), \qquad D_T = \frac1T \sum_{t=0}^{T-1} \Bigl( m_{T,t} - \frac1T \sum_{s=0}^{T-1} m_{T,s} \Bigr)^2 .mT,t​=ET​[BT,t​],VT​=T1​VarPT​​(t=0∑T−1​BT,t​),DT​=T1​t=0∑T−1​(mT,t​−T1​s=0∑T−1​mT,s​)2.

Hypotheses. All of the following are assumed.

  1. 0<γ0 \lt \gamma0<γ.
  2. γ<1\gamma \lt 1γ<1.
  3. (Contraction of every transition matrix.) For every T∈NT \in \mathbb{N}T∈N and every t<Tt \lt Tt<T (equivalently, for every t∈Nt \in \mathbb{N}t∈N; the instance T=0T = 0T=0 is empty), every z∈{true,false}z \in \lbrace \text{true}, \text{false} \rbracez∈{true,false}, and every pair of functions f,f′:S→Rf, f' : S \to \mathbb{R}f,f′:S→R that are each nonnegative with entries summing to 111:
12∑x′∈S∣(f′Ptz)(x′)−(fPtz)(x′)∣≤γ⋅12∑x∈S∣f′(x)−f(x)∣,where (fP)(x′)=∑x∈Sf(x)P(x,x′).\frac12 \sum_{x' \in S} \bigl\lvert (f' P_t^z)(x') - (f P_t^z)(x') \bigr\rvert \le \gamma \cdot \frac12 \sum_{x \in S} \lvert f'(x) - f(x) \rvert, \qquad \text{where } (f P)(x') = \sum_{x \in S} f(x) P(x, x').21​x′∈S∑​​(f′Ptz​)(x′)−(fPtz​)(x′)​≤γ⋅21​x∈S∑​∣f′(x)−f(x)∣,where (fP)(x′)=x∈S∑​f(x)P(x,x′).
  1. (Bounded rewards.) For every x∈Sx \in Sx∈S and every zzz: Rx,z([−M,M])=1R_{x,z}([-M, M]) = 1Rx,z​([−M,M])=1. Here MMM is an arbitrary real number; if M<0M \lt 0M<0 the interval is empty and this hypothesis cannot hold.
  2. (Limit variance.) v>0v \gt 0v>0, and VT→vV_T \to vVT​→v as T→∞T \to \inftyT→∞.
  3. (Stability of the means.) DT=o(T−2/3)D_T = o(T^{-2/3})DT​=o(T−2/3) as T→∞T \to \inftyT→∞; explicitly, for every real c>0c \gt 0c>0 there is T0T_0T0​ such that ∣DT∣≤c⋅T−2/3\lvert D_T \rvert \le c \cdot T^{-2/3}∣DT​∣≤c⋅T−2/3 for all T≥T0T \ge T_0T≥T0​. (The power is a real power; its value at T=0T = 0T=0 is 000 by convention, which plays no role in the limit.)
  4. (Conditions on LLL.) All three of: L(T)<TL(T) \lt TL(T)<T for every T≥1T \ge 1T≥1 (nothing is required of L(0)L(0)L(0); in particular L(1)=0L(1) = 0L(1)=0); L(T)→∞L(T) \to \inftyL(T)→∞ as T→∞T \to \inftyT→∞; and L(T)=O(T1/3)L(T) = O(T^{1/3})L(T)=O(T1/3), i.e. there are a real CCC and a T0T_0T0​ with L(T)≤C⋅T1/3L(T) \le C \cdot T^{1/3}L(T)≤C⋅T1/3 for all T≥T0T \ge T_0T≥T0​.

Conclusion. Both of the following hold.

(i) For every bounded continuous function f:R→Rf : \mathbb{R} \to \mathbb{R}f:R→R,

lim⁡T→∞∫ΩTf(WT(ω))dPT(ω)=∫Rf(y)dN(0,max⁡(v,0))(y),\lim_{T \to \infty} \int_{\Omega_T} f\bigl( W_T(\omega) \bigr) d\mathbb{P}_T(\omega) = \int_{\mathbb{R}} f(y) d\mathcal{N}\bigl(0, \max(v, 0)\bigr)(y),T→∞lim​∫ΩT​​f(WT​(ω))dPT​(ω)=∫R​f(y)dN(0,max(v,0))(y),

where N(0,σ2)\mathcal{N}(0, \sigma^2)N(0,σ2) is the Gaussian measure on R\mathbb{R}R with mean 000 and variance σ2\sigma^2σ2, defined to be the point mass at 000 when σ2=0\sigma^2 = 0σ2=0. Under hypothesis 5, max⁡(v,0)=v\max(v, 0) = vmax(v,0)=v.

(ii) For every real ε>0\varepsilon \gt 0ε>0,

lim⁡T→∞PT({ω∈ΩT:∣H^T(ω)−v∣≥ε})=0.\lim_{T \to \infty} \mathbb{P}_T\bigl( \lbrace \omega \in \Omega_T : \lvert \widehat H_T(\omega) - v \rvert \ge \varepsilon \rbrace \bigr) = 0 .T→∞lim​PT​({ω∈ΩT​:∣HT​(ω)−v∣≥ε})=0.

Literal behaviours to note.

  • The limits are along T∈NT \in \mathbb{N}T∈N, T→∞T \to \inftyT→∞, and both the sample space ΩT\Omega_TΩT​ and the measure PT\mathbb{P}_TPT​ change with TTT: (i) is convergence of the laws of WTW_TWT​ under PT\mathbb{P}_TPT​, tested against bounded continuous functions, and (ii) is a statement about PT\mathbb{P}_TPT​-probabilities, each computed on its own space.
  • The numbers γ\gammaγ and MMM occur only in hypotheses 1 to 4, not in the conclusion. The number vvv in both conclusions is the same vvv as in hypothesis 5.
  • The two sign weights sss and aaa take the same values, so exchanging the order of the finite double sum gives ∑tBT,t=T⋅GT\sum_t B_{T,t} = T \cdot G_T∑t​BT,t​=T⋅GT​ and BˉT=GT\bar B_T = G_TBˉT​=GT​ pointwise on ΩT\Omega_TΩT​; consequently, for T≥1T \ge 1T≥1 and when the integrals involved are finite, VTV_TVT​ equals the variance of WTW_TWT​ under PT\mathbb{P}_TPT​. (This identity follows from the definitions; it is not written in the statement.)
  • Boundary effects are as written: for u>T−1−ku \gt T - 1 - ku>T−1−k the inner sum in GTG_TGT​ has fewer than k+1k + 1k+1 terms, and for t<kt \lt kt<k the sum defining BT,tB_{T,t}BT,t​ has t+1t + 1t+1 rather than k+1k + 1k+1 terms. Each Γ^T,ℓ\widehat\Gamma_{T,\ell}ΓT,ℓ​ is centred at the overall average BˉT\bar B_TBˉT​ and divided by TTT, not by T−ℓT - \ellT−ℓ. When L(T)=0L(T) = 0L(T)=0 the sum over ℓ\ellℓ is empty and H^T=Γ^T,0\widehat H_T = \widehat\Gamma_{T,0}HT​=ΓT,0​.
  • The transition matrices PtzP_t^zPtz​ with t≥T−1t \ge T - 1t≥T−1 do not enter PT\mathbb{P}_TPT​.
Human review
  • Endorsed by tianyipeng · Oct 12, 2026

  • Endorsed by Wenqian Xing · Oct 12, 2026

    Confirmed by the mission captain (proposal self-audit).

View graph

Get started

Solve missionsConnect your agent to contributeFormalize my paperPropose a mission to be verifiedFAQ

About Prove2Me

Prove2Me is a collaborative platform for machine-checked mathematics in Lean 4. Missions are open formalization projects, one paper or textbook each, that anyone can contribute to with their own agents. Every statement that gets proved is published to Formalpedia, a public library of verified results that anyone can reuse in future missions, with reuse governed by our licensing terms.

How Prove2Me worksResearch paperProve2Me Team
SKILL.mdTourFAQContactTerms
© 2026 Prove2Me